Biography

Hongyi Li is a M.Eng. student at Xidian University, China, supervised by Professor Yongchao Wang. She is also a visiting student at Emory University since 2020, and her foreign advisor is Professor Liang Zhao. Before that, she received the B.Eng. degree (Hons.) in Telecommunications Engineering from Xidian University and graduated as the valedictorian of Xidian in 2019.

Research Interests

• Deep Learning On Graphs
• Nonconvex and Distributed Optimization
• Reliable and Explainable Deep Learning

News

• 04/2023: I serve as the PC member of the OPT for Machine Learning NeurIPS Workshop 2023.
• 11/2022: Our paper "Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM Framework" is accepted by TNNLS.
• 05/2022: I serve as the PC member of the OPT for Machine Learning NeurIPS Workshop 2022.

Publications

Journals

• Junxiang Wang, Hongyi Li (first-coauthor), Zheng Chai, Yongchao Wang, Yue Cheng, and Liang Zhao. Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM Framework, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), (Impact Factor: 14.255), accepted. [paper]
• Junxiang Wang, Hongyi Li, and Liang Zhao.Accelerated Gradient-free Neural Network Training by Multi-convex Alternating Optimization. Neurocomputing, (Impact Factor: 5.719), accepted. [paper]
• Junji Jiang, Chen Ling, Hongyi Li, Guangji Bai, Xujiang Zhao, and Liang Zhao. Quantifying Uncertainty in Graph Neural Network Explanations. Frontiers in Big Data, (Impact Factor: 3.1), accepted.[paper]

Workshops

• Hongyi Li, Junxiang Wang, Yongchao Wang, Yue Cheng, and Liang Zhao. Community-based Layerwise Distributed Training of Graph Convolutional Networks. NeurIPS 2021 Workshop on Optimization for Machine Learning (OPT 2021).  [paper][poster]
• Junxiang Wang,  Hongyi Li, Yongchao Wang, and Liang Zhao. Accelerated Gradient-free Neural Network Training by Multi-convex Alternating Optimization. Accepted by Workshop on ”Beyond first-order methods in ML systems” of the 38th International Conference on Machine Learning. [paper] [slides] [video]

Preprints

• Hongyi Li, Junxiang Wang, and Yongchao Wang. Edge Graph Neural Networks for Massive MIMO Detection. Preprint.  [paper]